Learning adaptive geometry for unsupervised domain adaptation

Unsupervised domain adaptation is an effective approach to solve the problem of dataset bias. However, most existing unsupervised domain adaptation methods assume that the geometry structures of data dis-tributions are similar in the source and target domains. This assumption is invalid in many practical applications, because the training and test datasets usually differ in the variability modes and/or variation degrees. This paper handles the problem of inconsistent geometries by aligning both data representations and geometries. To overcome the lack of target labels in aligning geometries, this paper proposes learning the adaptive geometry that is derived from the domain-shared label space. Source and target geometries are aligned by constraining them with the unified criteria of the adaptive geometry. Combining the adaptive geometry learning and adversarial learning techniques, we develop a geometry-aware dual-stream network to learn the geometry-aligned representations. Experimental results show that our method achieves good performance on cross-dataset recognition tasks. (c) 2020 Elsevier Ltd. All rights reserved.

Automated summary

This paper proposes a method to address dataset bias issues by aligning data representations and geometries to handle the problem of inconsistent geometries between source and target domains. By learning adaptive geometry and integrating adversarial learning techniques, a geometry-aware dual-stream network is developed to learn geometry-aligned representations.